Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 59 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.3927. Min Range: -1.3927
Max Act: 1.3927. Min Act: -0.0000
Data Index: 1062771 (The Pile)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.3927. Min Range: -1.3927
Max Act: 1.0759. Min Act: -0.0000
Data Index: 1249881 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.3927. Min Range: -1.3927
Max Act: 1.1324. Min Act: -0.0000
Data Index: 631116 (The Pile)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.8956. Min Act: -0.0000
Data Index: 1698874 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.3927. Min Range: -1.3927
Max Act: 1.0859. Min Act: -0.0000
Data Index: 32247 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.3927. Min Range: -1.3927
Max Act: 1.1419. Min Act: -0.0000
Data Index: 804184 (The Pile)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.9487. Min Act: 0.0000
Data Index: 19910 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.8321. Min Act: -0.0000
Data Index: 820466 (The Pile)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.9291. Min Act: -0.0000
Data Index: 959300 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.8533. Min Act: 0.0000
Data Index: 409769 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.8836. Min Act: 0.0000
Data Index: 655558 (The Pile)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.7913. Min Act: -0.0000
Data Index: 828968 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.9145. Min Act: 0.0000
Data Index: 1830705 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.7833. Min Act: -0.0000
Data Index: 826615 (The Pile)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.8337. Min Act: -0.0000
Data Index: 1291534 (The Pile)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.7195. Min Act: 0.0000
Data Index: 114660 (The Pile)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.7635. Min Act: 0.0000
Data Index: 1305197 (The Pile)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.7357. Min Act: -0.0000
Data Index: 145685 (The Pile)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.7534. Min Act: 0.0000
Data Index: 631113 (The Pile)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.3927. Min Range: -1.3927
Max Act: 0.7769. Min Act: 0.0000
Data Index: 715573 (The Pile)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19